2005-04-16 16:20:36 -06:00
|
|
|
/*
|
2008-08-02 03:55:55 -06:00
|
|
|
* arch/arm/include/asm/pgtable.h
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* Copyright (C) 1995-2002 Russell King
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*/
|
|
|
|
#ifndef _ASMARM_PGTABLE_H
|
|
|
|
#define _ASMARM_PGTABLE_H
|
|
|
|
|
|
|
|
#include <asm-generic/4level-fixup.h>
|
2006-06-20 13:46:52 -06:00
|
|
|
#include <asm/proc-fns.h>
|
|
|
|
|
|
|
|
#ifndef CONFIG_MMU
|
|
|
|
|
|
|
|
#include "pgtable-nommu.h"
|
|
|
|
|
|
|
|
#else
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#include <asm/memory.h>
|
2008-08-05 09:14:15 -06:00
|
|
|
#include <mach/vmalloc.h>
|
2006-12-13 07:34:43 -07:00
|
|
|
#include <asm/pgtable-hwdef.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2005-05-03 05:20:29 -06:00
|
|
|
/*
|
|
|
|
* Just any arbitrary offset to the start of the vmalloc VM area: the
|
|
|
|
* current 8MB value just means that there will be a 8MB "hole" after the
|
|
|
|
* physical memory until the kernel virtual memory starts. That means that
|
|
|
|
* any out-of-bounds memory accesses will hopefully be caught.
|
|
|
|
* The vmalloc() routines leaves a hole of 4kB between each vmalloced
|
|
|
|
* area for the same reason. ;)
|
|
|
|
*
|
|
|
|
* Note that platforms may override VMALLOC_START, but they must provide
|
|
|
|
* VMALLOC_END. VMALLOC_END defines the (exclusive) limit of this space,
|
|
|
|
* which may not overlap IO space.
|
|
|
|
*/
|
|
|
|
#ifndef VMALLOC_START
|
|
|
|
#define VMALLOC_OFFSET (8*1024*1024)
|
|
|
|
#define VMALLOC_START (((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
|
|
|
|
#endif
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* Hardware-wise, we have a two level page table structure, where the first
|
|
|
|
* level has 4096 entries, and the second level has 256 entries. Each entry
|
|
|
|
* is one 32-bit word. Most of the bits in the second level entry are used
|
|
|
|
* by hardware, and there aren't any "accessed" and "dirty" bits.
|
|
|
|
*
|
|
|
|
* Linux on the other hand has a three level page table structure, which can
|
|
|
|
* be wrapped to fit a two level page table structure easily - using the PGD
|
|
|
|
* and PTE only. However, Linux also expects one "PTE" table per page, and
|
|
|
|
* at least a "dirty" bit.
|
|
|
|
*
|
|
|
|
* Therefore, we tweak the implementation slightly - we tell Linux that we
|
|
|
|
* have 2048 entries in the first level, each of which is 8 bytes (iow, two
|
|
|
|
* hardware pointers to the second level.) The second level contains two
|
|
|
|
* hardware PTE tables arranged contiguously, followed by Linux versions
|
|
|
|
* which contain the state information Linux needs. We, therefore, end up
|
|
|
|
* with 512 entries in the "PTE" level.
|
|
|
|
*
|
|
|
|
* This leads to the page tables having the following layout:
|
|
|
|
*
|
|
|
|
* pgd pte
|
|
|
|
* | |
|
|
|
|
* +--------+ +0
|
|
|
|
* | |-----> +------------+ +0
|
|
|
|
* +- - - - + +4 | h/w pt 0 |
|
|
|
|
* | |-----> +------------+ +1024
|
|
|
|
* +--------+ +8 | h/w pt 1 |
|
|
|
|
* | | +------------+ +2048
|
|
|
|
* +- - - - + | Linux pt 0 |
|
|
|
|
* | | +------------+ +3072
|
|
|
|
* +--------+ | Linux pt 1 |
|
|
|
|
* | | +------------+ +4096
|
|
|
|
*
|
|
|
|
* See L_PTE_xxx below for definitions of bits in the "Linux pt", and
|
|
|
|
* PTE_xxx for definitions of bits appearing in the "h/w pt".
|
|
|
|
*
|
|
|
|
* PMD_xxx definitions refer to bits in the first level page table.
|
|
|
|
*
|
|
|
|
* The "dirty" bit is emulated by only granting hardware write permission
|
|
|
|
* iff the page is marked "writable" and "dirty" in the Linux PTE. This
|
|
|
|
* means that a write to a clean page will cause a permission fault, and
|
|
|
|
* the Linux MM layer will mark the page dirty via handle_pte_fault().
|
|
|
|
* For the hardware to notice the permission change, the TLB entry must
|
2007-07-17 05:03:03 -06:00
|
|
|
* be flushed, and ptep_set_access_flags() does that for us.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* The "accessed" or "young" bit is emulated by a similar method; we only
|
|
|
|
* allow accesses to the page if the "young" bit is set. Accesses to the
|
|
|
|
* page will cause a fault, and handle_pte_fault() will set the young bit
|
|
|
|
* for us as long as the page is marked present in the corresponding Linux
|
2007-07-17 05:03:03 -06:00
|
|
|
* PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is
|
|
|
|
* up to date.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* However, when the "young" bit is cleared, we deny access to the page
|
|
|
|
* by clearing the hardware PTE. Currently Linux does not flush the TLB
|
|
|
|
* for us in this case, which means the TLB will retain the transation
|
|
|
|
* until either the TLB entry is evicted under pressure, or a context
|
|
|
|
* switch which changes the user space mapping occurs.
|
|
|
|
*/
|
|
|
|
#define PTRS_PER_PTE 512
|
|
|
|
#define PTRS_PER_PMD 1
|
|
|
|
#define PTRS_PER_PGD 2048
|
|
|
|
|
|
|
|
/*
|
|
|
|
* PMD_SHIFT determines the size of the area a second-level page table can map
|
|
|
|
* PGDIR_SHIFT determines what a third-level page table entry can map
|
|
|
|
*/
|
|
|
|
#define PMD_SHIFT 21
|
|
|
|
#define PGDIR_SHIFT 21
|
|
|
|
|
|
|
|
#define LIBRARY_TEXT_START 0x0c000000
|
|
|
|
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
extern void __pte_error(const char *file, int line, unsigned long val);
|
|
|
|
extern void __pmd_error(const char *file, int line, unsigned long val);
|
|
|
|
extern void __pgd_error(const char *file, int line, unsigned long val);
|
|
|
|
|
|
|
|
#define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte_val(pte))
|
|
|
|
#define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd_val(pmd))
|
|
|
|
#define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd_val(pgd))
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
|
|
|
|
#define PMD_SIZE (1UL << PMD_SHIFT)
|
|
|
|
#define PMD_MASK (~(PMD_SIZE-1))
|
|
|
|
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
|
|
|
|
#define PGDIR_MASK (~(PGDIR_SIZE-1))
|
|
|
|
|
2005-04-19 14:29:21 -06:00
|
|
|
/*
|
|
|
|
* This is the lowest virtual address we can permit any user space
|
|
|
|
* mapping to be mapped at. This is particularly important for
|
|
|
|
* non-high vector CPUs.
|
|
|
|
*/
|
|
|
|
#define FIRST_USER_ADDRESS PAGE_SIZE
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#define FIRST_USER_PGD_NR 1
|
|
|
|
#define USER_PTRS_PER_PGD ((TASK_SIZE/PGDIR_SIZE) - FIRST_USER_PGD_NR)
|
|
|
|
|
2006-09-22 11:36:38 -06:00
|
|
|
/*
|
|
|
|
* section address mask and size definitions.
|
|
|
|
*/
|
|
|
|
#define SECTION_SHIFT 20
|
|
|
|
#define SECTION_SIZE (1UL << SECTION_SHIFT)
|
|
|
|
#define SECTION_MASK (~(SECTION_SIZE-1))
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* ARMv6 supersection address mask and size definitions.
|
|
|
|
*/
|
|
|
|
#define SUPERSECTION_SHIFT 24
|
|
|
|
#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT)
|
|
|
|
#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1))
|
|
|
|
|
|
|
|
/*
|
|
|
|
* "Linux" PTE definitions.
|
|
|
|
*
|
|
|
|
* We keep two sets of PTEs - the hardware and the linux version.
|
|
|
|
* This allows greater flexibility in the way we map the Linux bits
|
|
|
|
* onto the hardware tables, and allows us to have YOUNG and DIRTY
|
|
|
|
* bits.
|
|
|
|
*
|
|
|
|
* The PTE table pointer refers to the hardware entries; the "Linux"
|
|
|
|
* entries are stored 1024 bytes below.
|
|
|
|
*/
|
|
|
|
#define L_PTE_PRESENT (1 << 0)
|
|
|
|
#define L_PTE_YOUNG (1 << 1)
|
2009-07-11 09:57:20 -06:00
|
|
|
#define L_PTE_FILE (1 << 2) /* only when !PRESENT */
|
2008-09-06 11:53:37 -06:00
|
|
|
#define L_PTE_DIRTY (1 << 6)
|
|
|
|
#define L_PTE_WRITE (1 << 7)
|
|
|
|
#define L_PTE_USER (1 << 8)
|
|
|
|
#define L_PTE_EXEC (1 << 9)
|
2006-12-01 16:03:47 -07:00
|
|
|
#define L_PTE_SHARED (1 << 10) /* shared(v6), coherent(xsc3) */
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-09-06 13:04:59 -06:00
|
|
|
/*
|
|
|
|
* These are the memory types, defined to be compatible with
|
|
|
|
* pre-ARMv6 CPUs cacheable and bufferable bits: XXCB
|
|
|
|
*/
|
|
|
|
#define L_PTE_MT_UNCACHED (0x00 << 2) /* 0000 */
|
|
|
|
#define L_PTE_MT_BUFFERABLE (0x01 << 2) /* 0001 */
|
|
|
|
#define L_PTE_MT_WRITETHROUGH (0x02 << 2) /* 0010 */
|
|
|
|
#define L_PTE_MT_WRITEBACK (0x03 << 2) /* 0011 */
|
|
|
|
#define L_PTE_MT_MINICACHE (0x06 << 2) /* 0110 (sa1100, xscale) */
|
|
|
|
#define L_PTE_MT_WRITEALLOC (0x07 << 2) /* 0111 */
|
2008-09-06 14:07:45 -06:00
|
|
|
#define L_PTE_MT_DEV_SHARED (0x04 << 2) /* 0100 */
|
2008-09-06 13:04:59 -06:00
|
|
|
#define L_PTE_MT_DEV_NONSHARED (0x0c << 2) /* 1100 */
|
2008-09-06 14:07:45 -06:00
|
|
|
#define L_PTE_MT_DEV_WC (0x09 << 2) /* 1001 */
|
2008-09-06 13:04:59 -06:00
|
|
|
#define L_PTE_MT_DEV_CACHED (0x0b << 2) /* 1011 */
|
|
|
|
#define L_PTE_MT_MASK (0x0f << 2)
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
|
|
|
|
/*
|
2007-02-11 05:45:13 -07:00
|
|
|
* The pgprot_* and protection_map entries will be fixed up in runtime
|
|
|
|
* to include the cachable and bufferable bits based on memory policy,
|
|
|
|
* as well as any architecture dependent bits like global/ASID and SMP
|
|
|
|
* shared mapping bits.
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
2008-09-06 13:04:59 -06:00
|
|
|
#define _L_PTE_DEFAULT L_PTE_PRESENT | L_PTE_YOUNG
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2007-02-11 05:45:13 -07:00
|
|
|
extern pgprot_t pgprot_user;
|
2005-04-16 16:20:36 -06:00
|
|
|
extern pgprot_t pgprot_kernel;
|
|
|
|
|
2008-09-07 10:16:54 -06:00
|
|
|
#define _MOD_PROT(p, b) __pgprot(pgprot_val(p) | (b))
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-09-07 10:16:54 -06:00
|
|
|
#define PAGE_NONE pgprot_user
|
|
|
|
#define PAGE_SHARED _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_WRITE)
|
|
|
|
#define PAGE_SHARED_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_WRITE | L_PTE_EXEC)
|
|
|
|
#define PAGE_COPY _MOD_PROT(pgprot_user, L_PTE_USER)
|
|
|
|
#define PAGE_COPY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_EXEC)
|
|
|
|
#define PAGE_READONLY _MOD_PROT(pgprot_user, L_PTE_USER)
|
|
|
|
#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_EXEC)
|
|
|
|
#define PAGE_KERNEL pgprot_kernel
|
|
|
|
#define PAGE_KERNEL_EXEC _MOD_PROT(pgprot_kernel, L_PTE_EXEC)
|
|
|
|
|
|
|
|
#define __PAGE_NONE __pgprot(_L_PTE_DEFAULT)
|
|
|
|
#define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_WRITE)
|
|
|
|
#define __PAGE_SHARED_EXEC __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_WRITE | L_PTE_EXEC)
|
|
|
|
#define __PAGE_COPY __pgprot(_L_PTE_DEFAULT | L_PTE_USER)
|
|
|
|
#define __PAGE_COPY_EXEC __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_EXEC)
|
|
|
|
#define __PAGE_READONLY __pgprot(_L_PTE_DEFAULT | L_PTE_USER)
|
|
|
|
#define __PAGE_READONLY_EXEC __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_EXEC)
|
2007-02-11 05:45:13 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The table below defines the page protection levels that we insert into our
|
|
|
|
* Linux page table version. These get translated into the best that the
|
|
|
|
* architecture can perform. Note that on most ARM hardware:
|
|
|
|
* 1) We cannot do execute protection
|
|
|
|
* 2) If we could do execute protection, then read is implied
|
|
|
|
* 3) write implies read permissions
|
|
|
|
*/
|
2007-02-11 05:45:13 -07:00
|
|
|
#define __P000 __PAGE_NONE
|
|
|
|
#define __P001 __PAGE_READONLY
|
|
|
|
#define __P010 __PAGE_COPY
|
|
|
|
#define __P011 __PAGE_COPY
|
2008-09-07 10:16:54 -06:00
|
|
|
#define __P100 __PAGE_READONLY_EXEC
|
|
|
|
#define __P101 __PAGE_READONLY_EXEC
|
|
|
|
#define __P110 __PAGE_COPY_EXEC
|
|
|
|
#define __P111 __PAGE_COPY_EXEC
|
2007-02-11 05:45:13 -07:00
|
|
|
|
|
|
|
#define __S000 __PAGE_NONE
|
|
|
|
#define __S001 __PAGE_READONLY
|
|
|
|
#define __S010 __PAGE_SHARED
|
|
|
|
#define __S011 __PAGE_SHARED
|
2008-09-07 10:16:54 -06:00
|
|
|
#define __S100 __PAGE_READONLY_EXEC
|
|
|
|
#define __S101 __PAGE_READONLY_EXEC
|
|
|
|
#define __S110 __PAGE_SHARED_EXEC
|
|
|
|
#define __S111 __PAGE_SHARED_EXEC
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
/*
|
|
|
|
* ZERO_PAGE is a global shared page that is always zero: used
|
|
|
|
* for zero-mapped memory areas etc..
|
|
|
|
*/
|
|
|
|
extern struct page *empty_zero_page;
|
|
|
|
#define ZERO_PAGE(vaddr) (empty_zero_page)
|
|
|
|
|
|
|
|
#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT)
|
|
|
|
#define pfn_pte(pfn,prot) (__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
|
|
|
|
|
|
|
|
#define pte_none(pte) (!pte_val(pte))
|
2006-12-13 07:34:43 -07:00
|
|
|
#define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0)
|
2005-04-16 16:20:36 -06:00
|
|
|
#define pte_page(pte) (pfn_to_page(pte_pfn(pte)))
|
2006-09-26 00:31:48 -06:00
|
|
|
#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + __pte_index(addr))
|
2009-08-17 13:02:06 -06:00
|
|
|
|
|
|
|
#define pte_offset_map(dir,addr) (__pte_map(dir, KM_PTE0) + __pte_index(addr))
|
|
|
|
#define pte_offset_map_nested(dir,addr) (__pte_map(dir, KM_PTE1) + __pte_index(addr))
|
|
|
|
#define pte_unmap(pte) __pte_unmap(pte, KM_PTE0)
|
|
|
|
#define pte_unmap_nested(pte) __pte_unmap(pte, KM_PTE1)
|
|
|
|
|
|
|
|
#ifndef CONFIG_HIGHPTE
|
|
|
|
#define __pte_map(dir,km) pmd_page_vaddr(*(dir))
|
|
|
|
#define __pte_unmap(pte,km) do { } while (0)
|
|
|
|
#else
|
|
|
|
#define __pte_map(dir,km) ((pte_t *)kmap_atomic(pmd_page(*(dir)), km) + PTRS_PER_PTE)
|
|
|
|
#define __pte_unmap(pte,km) kunmap_atomic((pte - PTRS_PER_PTE), km)
|
|
|
|
#endif
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-12-13 07:34:43 -07:00
|
|
|
#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
|
|
|
|
|
2010-09-13 08:58:06 -06:00
|
|
|
#if __LINUX_ARM_ARCH__ < 6
|
|
|
|
static inline void __sync_icache_dcache(pte_t pteval)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
extern void __sync_icache_dcache(pte_t pteval);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
|
|
|
|
pte_t *ptep, pte_t pteval)
|
|
|
|
{
|
|
|
|
if (addr >= TASK_SIZE)
|
|
|
|
set_pte_ext(ptep, pteval, 0);
|
|
|
|
else {
|
|
|
|
__sync_icache_dcache(pteval);
|
|
|
|
set_pte_ext(ptep, pteval, PTE_EXT_NG);
|
|
|
|
}
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The following only work if pte_present() is true.
|
|
|
|
* Undefined behaviour if not..
|
|
|
|
*/
|
|
|
|
#define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT)
|
|
|
|
#define pte_write(pte) (pte_val(pte) & L_PTE_WRITE)
|
|
|
|
#define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY)
|
|
|
|
#define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG)
|
2010-09-13 08:58:06 -06:00
|
|
|
#define pte_exec(pte) (pte_val(pte) & L_PTE_EXEC)
|
mm: introduce pte_special pte bit
s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory
model (which is more dynamic than most). Instead, they had proposed to
implement it with an additional path through vm_normal_page(), using a bit in
the pte to determine whether or not the page should be refcounted:
vm_normal_page()
{
...
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
#ifdef s390
if (!mixedmap_refcount_pte(pte))
return NULL;
#else
if (!pfn_valid(pfn))
return NULL;
#endif
goto out;
}
...
}
This is fine, however if we are allowed to use a bit in the pte to determine
refcountedness, we can use that to _completely_ replace all the vma based
schemes. So instead of adding more cases to the already complex vma-based
scheme, we can have a clearly seperate and simple pte-based scheme (and get
slightly better code generation in the process):
vm_normal_page()
{
#ifdef s390
if (!mixedmap_refcount_pte(pte))
return NULL;
return pte_page(pte);
#else
...
#endif
}
And finally, we may rather make this concept usable by any architecture rather
than making it s390 only, so implement a new type of pte state for this.
Unfortunately the old vma based code must stay, because some architectures may
not be able to spare pte bits. This makes vm_normal_page a little bit more
ugly than we would like, but the 2 cases are clearly seperate.
So introduce a pte_special pte state, and use it in mm/memory.c. It is
currently a noop for all architectures, so this doesn't actually result in any
compiled code changes to mm/memory.o.
BTW:
I haven't put vm_normal_page() into arch code as-per an earlier suggestion.
The reason is that, regardless of where vm_normal_page is actually
implemented, the *abstraction* is still exactly the same. Also, while it
depends on whether the architecture has pte_special or not, that is the
only two possible cases, and it really isn't an arch specific function --
the role of the arch code should be to provide primitive functions and
accessors with which to build the core code; pte_special does that. We do
not want architectures to know or care about vm_normal_page itself, and
we definitely don't want them being able to invent something new there
out of sight of mm/ code. If we made vm_normal_page an arch function, then
we have to make vm_insert_mixed (next patch) an arch function too. So I
don't think moving it to arch code fundamentally improves any abstractions,
while it does practically make the code more difficult to follow, for both
mm and arch developers, and easier to misuse.
[akpm@linux-foundation.org: build fix]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Cc: Jared Hulbert <jaredeh@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 03:13:00 -06:00
|
|
|
#define pte_special(pte) (0)
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2010-09-13 08:58:06 -06:00
|
|
|
#define pte_present_user(pte) \
|
|
|
|
((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
|
|
|
|
(L_PTE_PRESENT | L_PTE_USER))
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#define PTE_BIT_FUNC(fn,op) \
|
|
|
|
static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
|
|
|
|
|
|
|
|
PTE_BIT_FUNC(wrprotect, &= ~L_PTE_WRITE);
|
|
|
|
PTE_BIT_FUNC(mkwrite, |= L_PTE_WRITE);
|
|
|
|
PTE_BIT_FUNC(mkclean, &= ~L_PTE_DIRTY);
|
|
|
|
PTE_BIT_FUNC(mkdirty, |= L_PTE_DIRTY);
|
|
|
|
PTE_BIT_FUNC(mkold, &= ~L_PTE_YOUNG);
|
|
|
|
PTE_BIT_FUNC(mkyoung, |= L_PTE_YOUNG);
|
|
|
|
|
mm: introduce pte_special pte bit
s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory
model (which is more dynamic than most). Instead, they had proposed to
implement it with an additional path through vm_normal_page(), using a bit in
the pte to determine whether or not the page should be refcounted:
vm_normal_page()
{
...
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
#ifdef s390
if (!mixedmap_refcount_pte(pte))
return NULL;
#else
if (!pfn_valid(pfn))
return NULL;
#endif
goto out;
}
...
}
This is fine, however if we are allowed to use a bit in the pte to determine
refcountedness, we can use that to _completely_ replace all the vma based
schemes. So instead of adding more cases to the already complex vma-based
scheme, we can have a clearly seperate and simple pte-based scheme (and get
slightly better code generation in the process):
vm_normal_page()
{
#ifdef s390
if (!mixedmap_refcount_pte(pte))
return NULL;
return pte_page(pte);
#else
...
#endif
}
And finally, we may rather make this concept usable by any architecture rather
than making it s390 only, so implement a new type of pte state for this.
Unfortunately the old vma based code must stay, because some architectures may
not be able to spare pte bits. This makes vm_normal_page a little bit more
ugly than we would like, but the 2 cases are clearly seperate.
So introduce a pte_special pte state, and use it in mm/memory.c. It is
currently a noop for all architectures, so this doesn't actually result in any
compiled code changes to mm/memory.o.
BTW:
I haven't put vm_normal_page() into arch code as-per an earlier suggestion.
The reason is that, regardless of where vm_normal_page is actually
implemented, the *abstraction* is still exactly the same. Also, while it
depends on whether the architecture has pte_special or not, that is the
only two possible cases, and it really isn't an arch specific function --
the role of the arch code should be to provide primitive functions and
accessors with which to build the core code; pte_special does that. We do
not want architectures to know or care about vm_normal_page itself, and
we definitely don't want them being able to invent something new there
out of sight of mm/ code. If we made vm_normal_page an arch function, then
we have to make vm_insert_mixed (next patch) an arch function too. So I
don't think moving it to arch code fundamentally improves any abstractions,
while it does practically make the code more difficult to follow, for both
mm and arch developers, and easier to misuse.
[akpm@linux-foundation.org: build fix]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Cc: Jared Hulbert <jaredeh@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 03:13:00 -06:00
|
|
|
static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
|
|
|
|
|
2009-11-20 14:06:43 -07:00
|
|
|
#define __pgprot_modify(prot,mask,bits) \
|
|
|
|
__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* Mark the prot value as uncacheable and unbufferable.
|
|
|
|
*/
|
2008-09-06 13:04:59 -06:00
|
|
|
#define pgprot_noncached(prot) \
|
2009-11-20 14:06:43 -07:00
|
|
|
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
|
2008-09-06 13:04:59 -06:00
|
|
|
#define pgprot_writecombine(prot) \
|
2009-11-20 14:06:43 -07:00
|
|
|
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
|
2010-05-15 04:02:43 -06:00
|
|
|
#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
|
2009-11-20 14:06:43 -07:00
|
|
|
#define pgprot_dmacoherent(prot) \
|
|
|
|
__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
|
2010-09-13 09:01:24 -06:00
|
|
|
#define __HAVE_PHYS_MEM_ACCESS_PROT
|
|
|
|
struct file;
|
|
|
|
extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
|
|
|
|
unsigned long size, pgprot_t vma_prot);
|
2009-11-20 14:06:43 -07:00
|
|
|
#else
|
|
|
|
#define pgprot_dmacoherent(prot) \
|
|
|
|
__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)
|
|
|
|
#endif
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#define pmd_none(pmd) (!pmd_val(pmd))
|
|
|
|
#define pmd_present(pmd) (pmd_val(pmd))
|
|
|
|
#define pmd_bad(pmd) (pmd_val(pmd) & 2)
|
|
|
|
|
|
|
|
#define copy_pmd(pmdpd,pmdps) \
|
|
|
|
do { \
|
|
|
|
pmdpd[0] = pmdps[0]; \
|
|
|
|
pmdpd[1] = pmdps[1]; \
|
|
|
|
flush_pmd_entry(pmdpd); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define pmd_clear(pmdp) \
|
|
|
|
do { \
|
|
|
|
pmdp[0] = __pmd(0); \
|
|
|
|
pmdp[1] = __pmd(0); \
|
|
|
|
clean_pmd_entry(pmdp); \
|
|
|
|
} while (0)
|
|
|
|
|
2006-09-26 00:31:48 -06:00
|
|
|
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
unsigned long ptr;
|
|
|
|
|
|
|
|
ptr = pmd_val(pmd) & ~(PTRS_PER_PTE * sizeof(void *) - 1);
|
|
|
|
ptr += PTRS_PER_PTE * sizeof(void *);
|
|
|
|
|
|
|
|
return __va(ptr);
|
|
|
|
}
|
|
|
|
|
2009-04-26 06:14:52 -06:00
|
|
|
#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Conversion functions: convert a page and protection to a page entry,
|
|
|
|
* and a page entry and page directory to the page they refer to.
|
|
|
|
*/
|
|
|
|
#define mk_pte(page,prot) pfn_pte(page_to_pfn(page),prot)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The "pgd_xxx()" functions here are trivial for a folded two-level
|
|
|
|
* setup: the pgd is never bad, and a pmd always exists (as it's folded
|
|
|
|
* into the pgd entry)
|
|
|
|
*/
|
|
|
|
#define pgd_none(pgd) (0)
|
|
|
|
#define pgd_bad(pgd) (0)
|
|
|
|
#define pgd_present(pgd) (1)
|
|
|
|
#define pgd_clear(pgdp) do { } while (0)
|
|
|
|
#define set_pgd(pgd,pgdp) do { } while (0)
|
|
|
|
|
|
|
|
/* to find an entry in a page-table-directory */
|
|
|
|
#define pgd_index(addr) ((addr) >> PGDIR_SHIFT)
|
|
|
|
|
|
|
|
#define pgd_offset(mm, addr) ((mm)->pgd+pgd_index(addr))
|
|
|
|
|
|
|
|
/* to find an entry in a kernel page-table-directory */
|
|
|
|
#define pgd_offset_k(addr) pgd_offset(&init_mm, addr)
|
|
|
|
|
|
|
|
/* Find an entry in the second-level page table.. */
|
|
|
|
#define pmd_offset(dir, addr) ((pmd_t *)(dir))
|
|
|
|
|
|
|
|
/* Find an entry in the third-level page table.. */
|
|
|
|
#define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
|
|
|
|
|
|
|
|
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
|
|
|
|
{
|
|
|
|
const unsigned long mask = L_PTE_EXEC | L_PTE_WRITE | L_PTE_USER;
|
|
|
|
pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
|
|
|
|
return pte;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
|
|
|
|
|
2009-07-05 04:30:15 -06:00
|
|
|
/*
|
|
|
|
* Encode and decode a swap entry. Swap entries are stored in the Linux
|
|
|
|
* page tables as follows:
|
|
|
|
*
|
|
|
|
* 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
|
|
|
|
* 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
|
2009-07-11 09:57:20 -06:00
|
|
|
* <--------------- offset --------------------> <- type --> 0 0 0
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
2009-07-11 09:57:20 -06:00
|
|
|
* This gives us up to 63 swap files and 32GB per swap file. Note that
|
2009-07-05 04:30:15 -06:00
|
|
|
* the offset field is always non-zero.
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
2009-07-11 09:57:20 -06:00
|
|
|
#define __SWP_TYPE_SHIFT 3
|
|
|
|
#define __SWP_TYPE_BITS 6
|
2009-07-05 04:30:15 -06:00
|
|
|
#define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1)
|
|
|
|
#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
|
|
|
|
|
|
|
|
#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
|
|
|
|
#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT)
|
|
|
|
#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
|
|
|
|
#define __swp_entry_to_pte(swp) ((pte_t) { (swp).val })
|
|
|
|
|
2009-07-05 04:30:15 -06:00
|
|
|
/*
|
|
|
|
* It is an error for the kernel to have more swap files than we can
|
|
|
|
* encode in the PTEs. This ensures that we know when MAX_SWAPFILES
|
|
|
|
* is increased beyond what we presently support.
|
|
|
|
*/
|
|
|
|
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
|
|
|
|
|
2009-07-05 04:52:21 -06:00
|
|
|
/*
|
|
|
|
* Encode and decode a file entry. File entries are stored in the Linux
|
|
|
|
* page tables as follows:
|
|
|
|
*
|
|
|
|
* 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
|
|
|
|
* 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
|
2009-07-11 09:57:20 -06:00
|
|
|
* <----------------------- offset ------------------------> 1 0 0
|
2009-07-05 04:52:21 -06:00
|
|
|
*/
|
|
|
|
#define pte_file(pte) (pte_val(pte) & L_PTE_FILE)
|
2009-07-11 09:57:20 -06:00
|
|
|
#define pte_to_pgoff(x) (pte_val(x) >> 3)
|
|
|
|
#define pgoff_to_pte(x) __pte(((x) << 3) | L_PTE_FILE)
|
2009-07-05 04:52:21 -06:00
|
|
|
|
2009-07-11 09:57:20 -06:00
|
|
|
#define PTE_FILE_MAX_BITS 29
|
2009-07-05 04:52:21 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
|
|
|
|
/* FIXME: this is not correct */
|
|
|
|
#define kern_addr_valid(addr) (1)
|
|
|
|
|
|
|
|
#include <asm-generic/pgtable.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We provide our own arch_get_unmapped_area to cope with VIPT caches.
|
|
|
|
*/
|
|
|
|
#define HAVE_ARCH_UNMAPPED_AREA
|
|
|
|
|
|
|
|
/*
|
2005-09-13 02:25:50 -06:00
|
|
|
* remap a physical page `pfn' of size `size' with page protection `prot'
|
2005-04-16 16:20:36 -06:00
|
|
|
* into virtual address `from'
|
|
|
|
*/
|
|
|
|
#define io_remap_pfn_range(vma,from,pfn,size,prot) \
|
|
|
|
remap_pfn_range(vma, from, pfn, size, prot)
|
|
|
|
|
|
|
|
#define pgtable_cache_init() do { } while (0)
|
|
|
|
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
|
2006-06-20 13:46:52 -06:00
|
|
|
#endif /* CONFIG_MMU */
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#endif /* _ASMARM_PGTABLE_H */
|